© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199545
    Prev
    Next
    INDEX
    Explanations

    temporal context

    np_acts-logits-general · gemini-2.5-flash-lite

    but not sufficient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पाण्या
    0.60
    iał
    0.55
    jeća
    0.52
    itelja
    0.52
    íticas
    0.50
    anjian
    0.50
    탉
    0.50
    անում
    0.50
    तां
    0.49
     पुनर्
    0.49
    POSITIVE LOGITS
     et
    0.51
    Event
    0.50
    1
    0.49
    FR
    0.48
    PR
    0.46
     corresponde
    0.45
    0
    0.45
     idx
    0.44
     evt
    0.43
     nun
    0.43
    Activations Density 0.001%

    No Known Activations